Interactive environment task execution on AppWorld normal (test)
4,554Avg@8 Success
CuES
Updated 19d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.12 | 4,554 | 4,524 | - | - | |
2025.12 | 3,316 | 3,473 | - | - | |
2025.12 | 3,098 | 2,848 | - | - | |
2025.12 | 2,879 | 3,212 | - | - | |
2025.12 | 1,776 | 2,143 | - | - | |
2025.12 | 1,176 | 1,429 | - | - | |
2025.12 | 300 | 325 | - | - | |
2025.12 | 125 | 187 | - | - | |
2025.10 | 65.8 | - | 72.6 | 58.9 | |
2025.10 | 61.3 | - | 67.3 | 55.4 | |
2025.10 | 60.2 | - | 66.7 | 53.6 | |
2025.10 | 58.9 | - | 62.5 | 55.4 | |
2025.10 | 56.2 | - | 64.3 | 48.2 | |
2025.10 | 54.2 | - | 61.9 | 46.4 | |
2025.12 | 0 | 23 | - | - | |
2026.03 | - | - | 69.6 | 50 | |
| - | - | 73.2 | 64.3 |